Patents by Inventor Jayesh Kumar Gupta

Jayesh Kumar Gupta has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Clifford neural layers for multivector system modeling
    Patent number: 12682225
    Abstract: Generally discussed herein are devices, systems, and methods for machine learning (ML) modeling of a system that operates on a multivector object. A method includes receiving, by an ML model, the multivector object as an input that represents a state of the multivector system. The method includes operating, by the ML model and using a Clifford layer that includes neurons that implement a multivector kernel, on the multivector input to generate a multivector output that represents the state of the multivector system responsive to the multivector input.
    Type: Grant
    Filed: December 22, 2022
    Date of Patent: July 14, 2026
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Johannes Brandstetter, Max Welling, Jayesh Kumar Gupta
  • CLIFFORD NEURAL LAYERS FOR MULTIVECTOR SYSTEM MODELING
    Publication number: 20240095506
    Abstract: Generally discussed herein are devices, systems, and methods for machine learning (ML) modeling of a system that operates on a multivector object. A method includes receiving, by an ML model, the multivector object as an input that represents a state of the multivector system. The method includes operating, by the ML model and using a Clifford layer that includes neurons that implement a multivector kernel, on the multivector input to generate a multivector output that represents the state of the multivector system responsive to the multivector input.
    Type: Application
    Filed: December 22, 2022
    Publication date: March 21, 2024
    Inventors: Johannes BRANDSTETTER, Max Welling, Jayesh Kumar Gupta